Precision Control of a Piezoceramic Actuator Using Neural Networks

In this paper, a control method combining the feedforward and feedback controllers is proposed to precisely control the dynamic performance of the piezoceramic actuator (PA). In the feedforward controller design, the hysteresis nonlinearity of the PA is modeled by using Preisach model first. Then a database of switching input/output values and a neural networks architecture treated as the inverse function of Preisach model are utilized in the feedforward controller In the feedback controller design, a PI controller is used to regulate the output error. Finally, some experimental results are validated the excellent tracking performances of the proposed controller.